# Meta-learning with implicit gradients in a few-shot setting for medical image segmentation

arXiv: https://arxiv.org/abs/2106.03223 · HTML: https://mlsanity.com/paper/2106.03223/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 52 references that are in the map.
- First posted on arXiv 6 Jun 2021.

## Builds on (most cited first, 27 of 27)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Attention U-Net: Learning Where to Look for the Pancreas](https://mlsanity.com/paper/1804.03999/) (2018)
- [Deeper, Broader and Artier Domain Generalization](https://mlsanity.com/paper/1710.03077/) (2017)
- [Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)](https://mlsanity.com/paper/1902.03368/) (2019)
- [Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations](https://mlsanity.com/paper/1707.03237/) (2017)
- [Kvasir-SEG: A Segmented Polyp Dataset](https://mlsanity.com/paper/1911.07069/) (2019)
- [Learning to Adapt Structured Output Space for Semantic Segmentation](https://mlsanity.com/paper/1802.10349/) (2018)
- [Meta-Learning with Implicit Gradients](https://mlsanity.com/paper/1909.04630/) (2019)
- [Domain Generalization via Model-Agnostic Learning of Semantic Features](https://mlsanity.com/paper/1910.13580/) (2019)
- [Unified Deep Supervised Domain Adaptation and Generalization](https://mlsanity.com/paper/1709.10190/) (2017)
- [Domain Generalization for Object Recognition with Multi-task Autoencoders](https://mlsanity.com/paper/1508.07680/) (2015)
- [CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learning](https://mlsanity.com/paper/1903.02351/) (2019)
- [A survey of loss functions for semantic segmentation](https://mlsanity.com/paper/2006.14822/) (2020)
- [Causality matters in medical imaging](https://mlsanity.com/paper/1912.08142/) (2019)
- [SG-One: Similarity Guidance Network for One-Shot Semantic Segmentation](https://mlsanity.com/paper/1810.09091/) (2018)
- [Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Loss](https://mlsanity.com/paper/1708.00961/) (2017)
- [Self-Supervision with Superpixels: Training Few-shot Medical Image Segmentation without Annotation](https://mlsanity.com/paper/2007.09886/) (2020)
- [Shape-aware Meta-learning for Generalizing Prostate MRI Segmentation to Unseen Domains](https://mlsanity.com/paper/2007.02035/) (2020)
- [CT Super-resolution GAN Constrained by the Identical, Residual, and Cycle Learning Ensemble(GAN-CIRCLE)](https://mlsanity.com/paper/1808.04256/) (2018)
- ['Squeeze & Excite' Guided Few-Shot Segmentation of Volumetric Images](https://mlsanity.com/paper/1902.01314/) (2019)
- [Kvasir-Instrument: Diagnostic and therapeutic tool segmentation dataset in gastrointestinal endoscopy](https://mlsanity.com/paper/2011.08065/) (2020)
- [Semi-supervised few-shot learning for medical image segmentation](https://mlsanity.com/paper/2003.08462/) (2020)
- [Domain Generalizer: A Few-shot Meta Learning Framework for Domain Generalization in Medical Imaging](https://mlsanity.com/paper/2008.07724/) (2020)
- [NanoNet: Real-Time Polyp Segmentation in Video Capsule Endoscopy and Colonoscopy](https://mlsanity.com/paper/2104.11138/) (2021)
- [Additive Angular Margin for Few Shot Learning to Classify Clinical Endoscopy Images](https://mlsanity.com/paper/2003.10033/) (2020)

## Built on by (most cited first, 15 of 15)

- [UniverSeg: Universal Medical Image Segmentation](https://mlsanity.com/paper/2304.06131/) (2023)
- [A Systematic Review of Few-Shot Learning in Medical Imaging](https://mlsanity.com/paper/2309.11433/) (2023)
- [Meta-learning approaches for few-shot learning: A survey of recent advances](https://mlsanity.com/paper/2303.07502/) (2023)
- [Few Shot Learning for Medical Imaging: A Comparative Analysis of Methodologies and Formal Mathematical Framework](https://mlsanity.com/paper/2305.04401/) (2023)
- [Learning to Adapt Foundation Model DINOv2 for Capsule Endoscopy Diagnosis](https://mlsanity.com/paper/2406.10508/) (2024)
- [Data efficient deep learning for medical image analysis: A survey](https://mlsanity.com/paper/2310.06557/) (2023)
- [Multi-task Explainable Skin Lesion Classification](https://mlsanity.com/paper/2310.07209/) (2023)
- [Rethinking Meta-Learning from a Learning Lens](https://mlsanity.com/paper/2409.08474/) (2024)
- [AwesomeMeta+: A Mixed-Prototyping Meta-Learning System Supporting AI Application Design Anywhere](https://mlsanity.com/paper/2304.12921/) (2023)
- [Harmonization Across Imaging Locations(HAIL): One-Shot Learning for Brain MRI](https://mlsanity.com/paper/2308.11047/) (2023)
- [A Feature Generator for Few-Shot Learning](https://mlsanity.com/paper/2409.14141/) (2024)
- [DREAMS: A python framework for Training Deep Learning Models on EEG Data with Model Card Reporting for Medical Applications](https://mlsanity.com/paper/2409.17815/) (2024)
- [MetaChest: Generalized few-shot learning of pathologies from chest X-rays](https://mlsanity.com/paper/2509.25590/) (2025)
- [Few-Shot Left Atrial Wall Segmentation in 3D LGE MRI via Meta-Learning](https://mlsanity.com/paper/2603.24985/) (2026)
- [Active few-shot segmentation by reinforcing data selection](https://mlsanity.com/paper/2607.22371/) (2026)

## Abstract (arXiv)

Widely used traditional supervised deep learning methods require a large number of training samples but often fail to generalize on unseen datasets. Therefore, a more general application of any trained model is quite limited for medical imaging for clinical practice. Using separately trained models for each unique lesion category or a unique patient population will require sufficiently large curated datasets, which is not practical to use in a real-world clinical set-up. Few-shot learning approaches can not only minimize the need for an enormous number of reliable ground truth labels that are labour-intensive and expensive but can also be used to model on a dataset coming from a new population. To this end, we propose to exploit an optimization-based implicit model agnostic meta-learning (iMAML) algorithm under few-shot settings for medical image segmentation. Our approach can leverage the learned weights from diverse but small training samples to perform analysis on unseen datasets with high accuracy. We show that, unlike classical few-shot learning approaches, our method improves generalization capability. To our knowledge, this is the first work that exploits iMAML for medical image segmentation and explores the strength of the model on scenarios such as meta-training on unique and mixed instances of lesion datasets. Our quantitative results on publicly available skin and polyp datasets show that the proposed method outperforms the naive supervised baseline model and two recent few-shot segmentation approaches by large margins. In addition, our iMAML approach shows an improvement of 2%-4% in dice score compared to its counterpart MAML for most experiments.